Enhancing Bias Assessment for Complex Term Groups in Language Embedding Models: Quantitative Comparison of Methods
Thus, the SD-WEAT shows promise for robustly measuring bias in the input embeddings fed to AI language models.
Authors
- Mariofanna Milanova (ORCID: https://orcid.org/0000-0003-0995-1921)
- Magnus Gray (ORCID: https://orcid.org/0009-0009-6355-7627)
- Leihong Wu (ORCID: https://orcid.org/0000-0002-4093-3708)
Institutions
- University of Arkansas at Little Rock (US)
- National Center for Toxicological Research (US)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2024-11-12
- DOI
- https://doi.org/10.2196/60272
- Citations
- 2
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.69